This has been my major concern, so much do that I'm going to be launching a tool to handle this specific task: agent conception and testing. There is so little visibility in the tools I've used that debug is just a game of whackamole.

Did you see this HN submission? https://news.ycombinator.com/item?id=46242838

It seems similar to what you're describing.

I did not. Thanks for the heads up!